Related papers: Feature-Aware Malicious Output Detection and Mitig…
We consider the challenge of mitigating the generation of negative or toxic content by the Large Language Models (LLMs) in response to certain prompts. We propose integrating risk-averse principles into LLM fine-tuning to minimize the…
Hateful memes have become a significant concern on the Internet, necessitating robust automated detection systems. While Large Multimodal Models (LMMs) have shown promise in hateful meme detection, they face notable challenges like…
Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…
Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…
Fine-tuning Large Language Models (LLMs) has emerged as a common practice for tailoring models to individual needs and preferences. The choice of datasets for fine-tuning can be diverse, introducing safety concerns regarding the potential…
Predictive modeling often faces challenges due to limited data availability and quality, especially in domains where collected features are weakly correlated with outcomes and where additional feature collection is constrained by ethical or…
Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…
The emergence of Large Language Models (LLMs) has significantly influenced various aspects of software development activities. Despite their benefits, LLMs also pose notable risks, including the potential to generate harmful content and…
Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of…
Large language models (LLMs) have shown great potential as general-purpose AI assistants in various domains. To meet the requirements of different applications, LLMs are often customized by further fine-tuning. However, the powerful…
Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such distribution shifts are often brittle and degrade performance…
Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…
The rising use of Large Language Models (LLMs) to create and disseminate malware poses a significant cybersecurity challenge due to their ability to generate and distribute attacks with ease. A single prompt can initiate a wide array of…
Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have been made to align these LLMs to human values using advanced…
Malicious domains are increasingly common and pose a severe cybersecurity threat. Specifically, many types of current cyber attacks use URLs for attack communications (e.g., C\&C, phishing, and spear-phishing). Despite the continuous…
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…
While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…
Recent advancements in Large Language Models (LLMs) have significantly enhanced their code generation capabilities. However, their robustness against adversarial misuse, particularly through multi-turn malicious coding prompts, remains…
Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…
This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align…